Learning the Geodesic Embedding with Graph Neural Networks

Abstract

We present GeGnn, a learning-based method for computing the approximate geodesic distance between two arbitrary points on discrete polyhedra surfaces with constant time complexity after fast precomputation. Previous relevant methods either focus on computing the geodesic distance between a single source and all destinations, which has linear complexity at least or require a long precomputation time. Our key idea is to train a graph neural network to embed an input mesh into a high-dimensional embedding space and compute the geodesic distance between a pair of points using the corresponding embedding vectors and a lightweight decoding function. To facilitate the learning of the embedding, we propose novel graph convolution and graph pooling modules that incorporate local geodesic information and are verified to be much more effective than previous designs. After training, our method requires only one forward pass of the network per mesh as precomputation. Then, we can compute the geodesic distance between a pair of points using our decoding function, which requires only several matrix multiplications and can be massively parallelized on GPUs. We verify the efficiency and effectiveness of our method on ShapeNet and demonstrate that our method is faster than existing methods by orders of magnitude while achieving comparable or better accuracy. Additionally, our method exhibits robustness on noisy and incomplete meshes and strong generalization ability on out-of-distribution meshes. The code and pretrained model can be found on https://github.com/IntelligentGeometry/GeGnn.

arXiv commentSIGGRAPH Asia 2023, Journal Track

References in corpus (11)

• Decoupled Weight Decay Regularization
• Neural Message Passing for Quantum Chemistry
• ShapeNet: An Information-Rich 3D Model Repository
• MeshCNN: A Network with an Edge
• Geodesics in Heat
• Point2Mesh: A Self-Prior for Deformable Meshes
• Subdivision-Based Mesh Convolution Networks
• Dual Octree Graph Networks for Learning Adaptive Volumetric Shape Representations
• A Survey of Algorithms for Geodesic Paths and Distances
• NeuroGF: A Neural Representation for Fast Geodesic Distance and Path Queries
• Parallel and Scalable Heat Methods for Geodesic Distance Computation

Cited by in corpus (2)

• Differentiable Geodesic Distance for Intrinsic Minimization on Triangle Meshes
• SharpNet: Enhancing MLPs to Represent Functions with Controlled Non-differentiability